I am a Phd student at the Idiap research institute and Ecole Polytechnique Federale de Lausanne, under the supervision of Mathew Magimai-Doss and Sebastien Marcel. The main goal of my PhD is to develop speaker recognition systems robust to presentation attacks by jointly learning relevant features and classifier from the raw speech signal with deep learning approaches, as well as understand the discriminative information learned by such systems.
Research interests: speaker recognition, spoofing attack detection, machine learning, audio/speech processing.
2014: Master in Communication Systems, Ecole Polytechnique Federale de Lausanne. Distinction: Research Scholars MSc Program.
Software Engineer Intern, Google, Speech team (New York, USA), 2018
Data Scientist, Starclay, Data Science start-up (Paris, France), 2015
Research intern, Universidad Politecnica de Madrid, Image Processing Group (Madrid, Spain), 2014.
Master thesis, IBM Research (Zurich, Switzerland), 2013 - 2014.
Research Assistant, EPFL, Laboratory of Security and Cryptography (Lausanne, Switzerland), 2012 - 2013. (part of the Research Scholars MSc Program)
For more details, check out my LinkedIn profile.
H. Muckenhirn, P. Korshunov, M. Magimai.-Doss and S. Marcel, "Long-Term Spectral Statistics for Voice Presentation Attack Detection", IEEE/ACM Transactions on Audio, Speech and Language Processing, 25(11):2098-2111, 2017.
H. Muckenhirn, M. Magimai.-Doss and S. Marcel, "On Learning Vocal Tract System Related Speaker Discriminative Information from Raw Signal Using CNNs", Interspeech, 2018.
S. H. Kabil, H. Muckenhirn and M. Magimai.-Doss, "On Learning to Identify Genders from Raw Speech Signal Using CNNs", Interspeech, 2018.
H. Muckenhirn, M. Magimai.-Doss and S. Marcel, "Towards directly modeling raw speech signal for speaker verification using CNNs", ICASSP, 2018.
H. Muckenhirn, M. Magimai.-Doss and S. Marcel, "End-to-End Convolutional Neural Network-based Voice Presentation Attack Detection", International Joint Conference on Biometrics, 2017.
P. Korshunov, S. Marcel, H. Muckenhirn et al., "Overview of BTAS 2016 Speaker Anti-spoofing Competition", International Conference on Biometrics: Theory, Applications and Systems, 2016.
H. Muckenhirn, M. Magimai.-Doss and S. Marcel, "Presentation Attack Detection Using Long-Term Spectral Statistics for Trustworthy Speaker Verification", International Conference of the Biometrics Special Interest Group, 2016.
Currently under review
Q. Wang*, H. Muckenhirn*, K. Wilson, P. Sridhar, Z. Wu, J. Hershey, R. A. Saurous, R. J. Weiss, Y. Jia, I. Lopez Moreno, "Voicefilter: Targeted voice separation by speaker-conditioned spectrogram masking", submitted to ICASSP 2019.
H. Muckenhirn, V. Abrol, M. Magimai.-Doss and S. Marcel, "Gradient-based visualization of CNNs using raw waveforms", submitted to ICASSP 2019.
Misc. PhD activities
Attended the Google Speech Summit in London, 2018. (poster presentation)
Attended the IEEE-EURASIP Summer School on Signal Processing, Signal Processing meets Deep Learning, in Capri, 2017. (poster presentation)
Presented during the Swiss Machine Learning Day, 2016.
Reviewed papers for Interspeech 2017, Interspeech 2018 and IEEE Robotics and Automation Letters.